CA2985839A1 - Health lending system and method using probabilistic graph models - Google Patents
Health lending system and method using probabilistic graph modelsInfo
- Publication number
- CA2985839A1 CA2985839A1 CA2985839A CA2985839A CA2985839A1 CA 2985839 A1 CA2985839 A1 CA 2985839A1 CA 2985839 A CA2985839 A CA 2985839A CA 2985839 A CA2985839 A CA 2985839A CA 2985839 A1 CA2985839 A1 CA 2985839A1
- Authority
- CA
- Canada
- Prior art keywords
- graph
- health
- risk
- bayes
- health service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Technology Law (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
Abstract
A system and method for health lending using a probabilistic graph model are described. The system and method may generate a health credit score ("HICO"). The HICO is a score that is a risk measure placed on all entities of a healthcare transaction in which a company that owns or operates the system may have an interest or a company that utilizes the HICO score for its risk assessment.
Description
HEALTH LENDING SYSTEM AND METHOD USING PROBABILISTIC GRAPH MODELS
Theodore C. Tanner, Jr.
Colin Erik Alstad Priority Claim/Related Application This application claims the benefit under 35 USC 119(e) and priority under 35 to U.S. Provisional Patent Application Serial No. 62/105,503, filed on January 20, 2015, and entitled "Health Lending System and Method Using Probabilistic Graph Models", the entirety of which is incorporated herein by reference.
Field The disclosure relates generally to a health system and method and in particular to a health lending system and method.
Background The problem of fmancial credit scoring is a very challenging and important financial analysis problem. The main challenge with the credit risk modeling and assessment is that the current models are riddled with uncertainty. The estimation of the probability of default (insolvency), modeling correlation structure for a group of connected borrowers and estimation of amount of correlation are the most important sources of uncertainty that can severely impair the quality of credit risk models.
Many techniques have already been proposed to tackle this problem, ranging from statistical classifiers to decision trees, nearest-neighbor methods and neural networks. Although the latter are powerful pattern recognition techniques, their use for practical problem solving (and credit scoring) is rather limited due to their intrinsic opaque, black box nature. The best known method in the industry is the Fair Isaac Corporation (FICO ) score. The FICO
score is calculated from several different pieces of credit data in a credit report of a user. The data may be grouped into five categories as shown in Figure 1. The percentages in the chart in Figure 1 reflect how important each of the categories is in determining how the FICO score of each user is calculated.
The FICO Score considers both positive and negative information in a credit report. For example, late payments will lower your FICO Score, but establishing or re-establishing a good track record of making payments on time will raise your score. There are several credit reporting
Theodore C. Tanner, Jr.
Colin Erik Alstad Priority Claim/Related Application This application claims the benefit under 35 USC 119(e) and priority under 35 to U.S. Provisional Patent Application Serial No. 62/105,503, filed on January 20, 2015, and entitled "Health Lending System and Method Using Probabilistic Graph Models", the entirety of which is incorporated herein by reference.
Field The disclosure relates generally to a health system and method and in particular to a health lending system and method.
Background The problem of fmancial credit scoring is a very challenging and important financial analysis problem. The main challenge with the credit risk modeling and assessment is that the current models are riddled with uncertainty. The estimation of the probability of default (insolvency), modeling correlation structure for a group of connected borrowers and estimation of amount of correlation are the most important sources of uncertainty that can severely impair the quality of credit risk models.
Many techniques have already been proposed to tackle this problem, ranging from statistical classifiers to decision trees, nearest-neighbor methods and neural networks. Although the latter are powerful pattern recognition techniques, their use for practical problem solving (and credit scoring) is rather limited due to their intrinsic opaque, black box nature. The best known method in the industry is the Fair Isaac Corporation (FICO ) score. The FICO
score is calculated from several different pieces of credit data in a credit report of a user. The data may be grouped into five categories as shown in Figure 1. The percentages in the chart in Figure 1 reflect how important each of the categories is in determining how the FICO score of each user is calculated.
The FICO Score considers both positive and negative information in a credit report. For example, late payments will lower your FICO Score, but establishing or re-establishing a good track record of making payments on time will raise your score. There are several credit reporting
-2-companies that work in conjunction with each other, such as Equifax and Transunion to name but a few organizations. However these companies are not able to properly align themselves to a risk management model that matches health based loans. Specifically they do not know the demographics, the place of living, the occupation, the length of employment and dependents of the person. Further in the case of health based services and loans, the risk are increased due to the unhealthy nature of the consumer who is getting the health service and must pay back the loan.
The recent upsurge in health care costs has seen an increased interest in lending to consumers for health services. It is desirable to provide a system and method for determining a health credit score that models the risk of a health care loan to a consumer.
Brief Description of the Drawings Figure 1 illustrates an example of a known FICO score;
Figure 2 illustrates a health services system that may incorporate a health lending system;
Figure 3 illustrates more details of the health lending system;
Figure 4 illustrates a method for predicting risk;
Figure 5 illustrates an example of a provider Bayes risk network;
Figure 6 illustrates an example of a method for a provider Bayes model generation;
Figure 7 illustrates an example of a method for consumer risk modeling;
Figure 8 illustrates an example of the output of the BeliefNetwork graph inference model;
Figure 9 illustrates an example of a PDHICO Provider/Payer example input data for the risk assessment;
Figure 10 illustrates an example of a risk graph for the PDHICO Provider/Payer example data in Figure 9;
Figure 11 illustrates an example of the output of the system for the PDHICO
Provider/Payer example data in Figure 9;
Figure 12 illustrates an example of a PDHICO Consumer example input data for the risk assessment;
Figure 13 illustrates an example of a risk graph for the PDHICO consumer example data in Figure 12; and
The recent upsurge in health care costs has seen an increased interest in lending to consumers for health services. It is desirable to provide a system and method for determining a health credit score that models the risk of a health care loan to a consumer.
Brief Description of the Drawings Figure 1 illustrates an example of a known FICO score;
Figure 2 illustrates a health services system that may incorporate a health lending system;
Figure 3 illustrates more details of the health lending system;
Figure 4 illustrates a method for predicting risk;
Figure 5 illustrates an example of a provider Bayes risk network;
Figure 6 illustrates an example of a method for a provider Bayes model generation;
Figure 7 illustrates an example of a method for consumer risk modeling;
Figure 8 illustrates an example of the output of the BeliefNetwork graph inference model;
Figure 9 illustrates an example of a PDHICO Provider/Payer example input data for the risk assessment;
Figure 10 illustrates an example of a risk graph for the PDHICO Provider/Payer example data in Figure 9;
Figure 11 illustrates an example of the output of the system for the PDHICO
Provider/Payer example data in Figure 9;
Figure 12 illustrates an example of a PDHICO Consumer example input data for the risk assessment;
Figure 13 illustrates an example of a risk graph for the PDHICO consumer example data in Figure 12; and
-3-Figure 14 illustrates an example of the output of the system for the PDHICO
consumer example data in Figure 12.
Detailed Description of One or More Embodiments The disclosure is particularly applicable to a cloud based system and method for health lending using a health credit ("HICO") score that may be generated from a probabilistic graph model and it is in this context that the disclosure will be described. It will be appreciated, however, that the system and method has greater utility since it may use other models in order to generate the RICO and may be implemented in different manners that those described below that would be within the scope of the disclosure. Although the health lending system is shown integrated with a health services system in the figures and descriptions below, the health lending system also may be a standalone system or integrated into other systems.
The health credit score ("HICO") generated by the system and method described below has several factors that differentiate the RICO from the credit score described above. The RICO
is a score that is a risk measure placed on all entities of a healthcare transaction in which a company that owns or operates the system may have an interest or a company that utilizes the RICO score for its risk assessment. Each entity may be a health service consumer, a health service provider or a health service payer. However, the system and method described herein may be used to perform a risk measure on various other entities that are part of the health services industry or space. For purposes of illustration below, the description below may consider the entity types described above and then consider the specific risk each entity poses as well as the data and models that may be used to generate the RICO.
Figure 2 illustrates a health services system 100 that may incorporate a health lending system. The health services system 100 may have one or more computing devices 102 that connect over a communication path 106 to a backend system 108. Each computing device 102, such as computing devices 102a, 102b, 102n as shown in Figure 1, may be a processor based device with memory, persistent storage, wired or wireless communication circuits and a display that allows each computing device to connect to and couple over the communication path 106 to a backend system 108. For example, each computing device may be a smartphone device, such as an Apple Computer product, Android OS based product, etc., a tablet computer, a personal computer, a terminal device, a laptop computer and the like. In one embodiment shown in Figure
consumer example data in Figure 12.
Detailed Description of One or More Embodiments The disclosure is particularly applicable to a cloud based system and method for health lending using a health credit ("HICO") score that may be generated from a probabilistic graph model and it is in this context that the disclosure will be described. It will be appreciated, however, that the system and method has greater utility since it may use other models in order to generate the RICO and may be implemented in different manners that those described below that would be within the scope of the disclosure. Although the health lending system is shown integrated with a health services system in the figures and descriptions below, the health lending system also may be a standalone system or integrated into other systems.
The health credit score ("HICO") generated by the system and method described below has several factors that differentiate the RICO from the credit score described above. The RICO
is a score that is a risk measure placed on all entities of a healthcare transaction in which a company that owns or operates the system may have an interest or a company that utilizes the RICO score for its risk assessment. Each entity may be a health service consumer, a health service provider or a health service payer. However, the system and method described herein may be used to perform a risk measure on various other entities that are part of the health services industry or space. For purposes of illustration below, the description below may consider the entity types described above and then consider the specific risk each entity poses as well as the data and models that may be used to generate the RICO.
Figure 2 illustrates a health services system 100 that may incorporate a health lending system. The health services system 100 may have one or more computing devices 102 that connect over a communication path 106 to a backend system 108. Each computing device 102, such as computing devices 102a, 102b, 102n as shown in Figure 1, may be a processor based device with memory, persistent storage, wired or wireless communication circuits and a display that allows each computing device to connect to and couple over the communication path 106 to a backend system 108. For example, each computing device may be a smartphone device, such as an Apple Computer product, Android OS based product, etc., a tablet computer, a personal computer, a terminal device, a laptop computer and the like. In one embodiment shown in Figure
-4-2, each computing device 102 may store an application 104 in memory and then execute that application using the processor of the computing device to interface with the backend system.
For example, the application may be a typical browser application or may be a mobile application.
The communication path 106 may be a wired or wireless communication path that uses a secure protocol or an unsecure protocol. For example, the communication path 106 may be the Internet, Ethernet, a wireless data network, a cellular digital data network, a WiFi network and the like.
The backend system 108 may have a health marketplace engine 110 and a health lending system 113 that may be coupled together. Each of these components of the backend system may be implemented using one or more computing resources, such as one or more server computers, one or more cloud computing resources and the like. In one embodiment, the health marketplace engine 110 and the health lending system 113 may each be implemented in software in which each has a plurality of lines of computer code that are executed by a processor of the one or more computing resources of the backend system. Thus, in that embodiment, the processor of the one or more computing resources of the backend system is configured to perform the operations and functions of the marketplace and health lending system as described below. In other embodiments, each of the health marketplace engine 110 and the health lending system 113 may be implemented in hardware such as a programmed logic device, a programmed processor or microcontroller and the like. The backend system 108 may be coupled to a store 114 that stores the various data and software modules that make up the healthcare system and the health lending system. The store 114 may be implemented as a hardware database system, a software database system or any other storage system.
The health marketplace engine 110 may allow practitioners that have joined the healthcare social community to reach potential clients in ways unimaginable even a few years ago. In addition to giving practitioners a social portal with which to communicate and market themselves with consumers, the marketplace gives each healthcare practitioner the ability to offer their services in an environment that is familiar to users of Groupon, Living Social, or other social marketplaces.
The health lending system, as described below, is a system that receives data about an entity involved in a health services transaction and then generates a risk measure for the entity involved in the health services transaction. In one embodiment, the risk measure may be in the
For example, the application may be a typical browser application or may be a mobile application.
The communication path 106 may be a wired or wireless communication path that uses a secure protocol or an unsecure protocol. For example, the communication path 106 may be the Internet, Ethernet, a wireless data network, a cellular digital data network, a WiFi network and the like.
The backend system 108 may have a health marketplace engine 110 and a health lending system 113 that may be coupled together. Each of these components of the backend system may be implemented using one or more computing resources, such as one or more server computers, one or more cloud computing resources and the like. In one embodiment, the health marketplace engine 110 and the health lending system 113 may each be implemented in software in which each has a plurality of lines of computer code that are executed by a processor of the one or more computing resources of the backend system. Thus, in that embodiment, the processor of the one or more computing resources of the backend system is configured to perform the operations and functions of the marketplace and health lending system as described below. In other embodiments, each of the health marketplace engine 110 and the health lending system 113 may be implemented in hardware such as a programmed logic device, a programmed processor or microcontroller and the like. The backend system 108 may be coupled to a store 114 that stores the various data and software modules that make up the healthcare system and the health lending system. The store 114 may be implemented as a hardware database system, a software database system or any other storage system.
The health marketplace engine 110 may allow practitioners that have joined the healthcare social community to reach potential clients in ways unimaginable even a few years ago. In addition to giving practitioners a social portal with which to communicate and market themselves with consumers, the marketplace gives each healthcare practitioner the ability to offer their services in an environment that is familiar to users of Groupon, Living Social, or other social marketplaces.
The health lending system, as described below, is a system that receives data about an entity involved in a health services transaction and then generates a risk measure for the entity involved in the health services transaction. In one embodiment, the risk measure may be in the
-5-form of a health credit score ("HICO") that is a risk measure placed on all entities of a healthcare or health services transaction for a company that owns or operates the system may have an interest or a company that utilizes the RICO score for its risk assessment.
Each entity may be a health service consumer, a health service provider or a health service payer.
However, the system and method described herein may be used to perform a risk measure on various other entities that are part of the health services industry or space. In one embodiment, the risk measure may be based on a probabilistic graph model as described below.
Figure 3 illustrates more details of the health lending system 113. The health lending system 113 may have an input processor 300 that receives health data input information about an entity and processes it for use by the health lending system 113 such as by, for example, performing an ETL process. The output from the input processor may be fed into a graph model engine 302 that generates a probabilistic graph model based on the health data information for the entity and the output from the graph model engine 302 may be fed into a health credit score generator 304 that generates a health credit score for the entity based on the probabilistic graph model.
Now, the health data input information for the health lending system is described in more detail. The health data input information may include one or more vectors of data that may be generated by an "Extract Transform and Load Process (ETL)" and accessible via the health system using Application Programmer Interfaces (APIs). An example of the data entities that may be used for the Probabilistic Graph structure(s) and the graph model engine 302 appear below.
However, additional or other data vectors may be used and those other data vectors may be from other ETL processes. Thus, the example data vectors below are merely illustrative and the disclosure is directed to various different types of data vectors that may be used by the graph model engine.
Consumer Entity In some embodiments, the health services system may be a hybrid bank/insurer in which the consumers present two possible risk profiles. Specifically, the health services system may provide consumers with traditional health insurance as well as lend them money to pay for health services.
Health Services Lending
Each entity may be a health service consumer, a health service provider or a health service payer.
However, the system and method described herein may be used to perform a risk measure on various other entities that are part of the health services industry or space. In one embodiment, the risk measure may be based on a probabilistic graph model as described below.
Figure 3 illustrates more details of the health lending system 113. The health lending system 113 may have an input processor 300 that receives health data input information about an entity and processes it for use by the health lending system 113 such as by, for example, performing an ETL process. The output from the input processor may be fed into a graph model engine 302 that generates a probabilistic graph model based on the health data information for the entity and the output from the graph model engine 302 may be fed into a health credit score generator 304 that generates a health credit score for the entity based on the probabilistic graph model.
Now, the health data input information for the health lending system is described in more detail. The health data input information may include one or more vectors of data that may be generated by an "Extract Transform and Load Process (ETL)" and accessible via the health system using Application Programmer Interfaces (APIs). An example of the data entities that may be used for the Probabilistic Graph structure(s) and the graph model engine 302 appear below.
However, additional or other data vectors may be used and those other data vectors may be from other ETL processes. Thus, the example data vectors below are merely illustrative and the disclosure is directed to various different types of data vectors that may be used by the graph model engine.
Consumer Entity In some embodiments, the health services system may be a hybrid bank/insurer in which the consumers present two possible risk profiles. Specifically, the health services system may provide consumers with traditional health insurance as well as lend them money to pay for health services.
Health Services Lending
-6-In the context of lending money for health services (including health care procedures), the main risk is that the consumer defaults on the loan, thus the main metrics for determining default risk will probably be measures like the known FICO credit score, credit history, available assets (liquid and non-liquid), willingness and/or ability to back the loan by collateral, etc. The overall current FICO model for creditworthiness breaks down as follows:
= 35% Payment History = 30% Debt Burden = 15% Length of credit history = 10% Types of credit used = 10% Recent searches for credit Health Insurance The setting of risk adjustment in terms of health insurance premiums is an extremely complicated and regulated (especially under the ACA) process. The system may also collect data on plan members that may not be a part of the usual risk models in exchange for lower premiums.
These datasets could possibly include data from personal wearable devices (Fitbit, Jawbone, smartphone apps) that track lifestyle and biological measurements, as well as past medical records.
For health insurance lending, the health system may have the following information about each person who wants health insurance.
= Basic demographics (i.e. location, gender, DOB) Insurance Information = Member ID
= Group ID
= Total deductible = Remaining deductible = Dependents Marketplace Interactions = Specialties Searched = Conditions Searched = Purchases made
= 35% Payment History = 30% Debt Burden = 15% Length of credit history = 10% Types of credit used = 10% Recent searches for credit Health Insurance The setting of risk adjustment in terms of health insurance premiums is an extremely complicated and regulated (especially under the ACA) process. The system may also collect data on plan members that may not be a part of the usual risk models in exchange for lower premiums.
These datasets could possibly include data from personal wearable devices (Fitbit, Jawbone, smartphone apps) that track lifestyle and biological measurements, as well as past medical records.
For health insurance lending, the health system may have the following information about each person who wants health insurance.
= Basic demographics (i.e. location, gender, DOB) Insurance Information = Member ID
= Group ID
= Total deductible = Remaining deductible = Dependents Marketplace Interactions = Specialties Searched = Conditions Searched = Purchases made
-7-= Log in frequency = Providers rated/reviewed Self reported Health Statistics via Wearable APIs = BM
= Smoker status = Activity Level = Wellness program memberships Financial Information = FICO Credit Score = Credit reports = Assets/Debts = Lending data from Lending Club Social Network interaction data = twitter, facebook, linked Wearable API Data = Measured activity level = Sleep cycles Provider Entities In addition to processing insurance claims for providers, the health lending system may also immediately pay providers for their services instead of them having to wait for the payer to process a claim and then the health lending system is reimbursed from the payer. The risk in immediately paying providers for services rendered is that either the price we pay the provider is more than the price that will be reimbursed by the payer or worse that the service is not covered at all by the consumer's insurance. An analysis of current trends shows that on average for both private insurance and Medicare, providers submit claims for higher than the allowed price with the mentality for providers to bill at the highest price and hope for the best.
The application of the current system accurately predicts what a payer is actually going to pay for a given claim so that we can minimize the number of transactions where the amount we pay the provider is higher than the amount reimbursed by the payer.
The health lending system has various information about each provider including:
= Smoker status = Activity Level = Wellness program memberships Financial Information = FICO Credit Score = Credit reports = Assets/Debts = Lending data from Lending Club Social Network interaction data = twitter, facebook, linked Wearable API Data = Measured activity level = Sleep cycles Provider Entities In addition to processing insurance claims for providers, the health lending system may also immediately pay providers for their services instead of them having to wait for the payer to process a claim and then the health lending system is reimbursed from the payer. The risk in immediately paying providers for services rendered is that either the price we pay the provider is more than the price that will be reimbursed by the payer or worse that the service is not covered at all by the consumer's insurance. An analysis of current trends shows that on average for both private insurance and Medicare, providers submit claims for higher than the allowed price with the mentality for providers to bill at the highest price and hope for the best.
The application of the current system accurately predicts what a payer is actually going to pay for a given claim so that we can minimize the number of transactions where the amount we pay the provider is higher than the amount reimbursed by the payer.
The health lending system has various information about each provider including:
-8-Provider Demographics (age, gender, location) Medical Education = Where and when they went to medical school = Where and when they did their residencies/fellowships = Specialties = Credentials = Hospital affiliations Pricing = Submitted and paid prices from medicare = Cash prices = Services listed on the marketplace = Responses to requests for quote Ratings, Reviews, Recognitions = Reviews and ratings from marketplace = Malpractice Sanctions from state licensure bodies we receive from the American Medical Association = Ratings and Reviews Claims Statistics = Number of claims submitted, submitted price, reimbursed price per procedure = Number of rejected claims per procedure Paver Entities (aka Insurance Carriers, Trading Partners) In the situation where the health lending system immediately remit payment to a provider for a service, the health lending system then submits the claim to the payer to collect payment.
Like with the providers, the main risk is in the amount reimbursed from the payer for a service and the length of time it takes for the reimbursement.
The health lending system has various information about each payer including (from the processing of X12 transactions):
= Payment Statistics: How much does payer X pay on average for procedure Y.
= Statistics about time taken to process claims (i.e. average processing time, average time per procedure, etc.)
Like with the providers, the main risk is in the amount reimbursed from the payer for a service and the length of time it takes for the reimbursement.
The health lending system has various information about each payer including (from the processing of X12 transactions):
= Payment Statistics: How much does payer X pay on average for procedure Y.
= Statistics about time taken to process claims (i.e. average processing time, average time per procedure, etc.)
9 = Statistics about rejected claims. Analysis of claims in general and claims segmented by payer will probably allow us to build predictive models for determining the probability that a claim will be rejected.
Thus, for each of the above entities, the health lending system may assess or predict the risk associated with the transaction with each of the above entities. The risk prediction may be a mixture of the three scores based on a probability model.
Figure 4 illustrates a method 400 for predicting risk for each of the different entities that may be performed, in one embodiment, by the health lending system 113 shown in Figures 2-3.
The method illustrated in Figure 4 also may be performed by software that is a plurality of lines of computer code that may be executed by a processor of the one or more computing resources so that the processor is configured to perform the operations and functions of the risk prediction as described below. In other embodiments, the method may be performed using hardware such as a programmed logic device, a programmed processor, a microcontroller, an application specific integrated circuit and the like.
As shown in Figure 4, the method may receive, for a payor, information for the risk prediction based on processing claims and benefits (examples of which are set forth above) via ETL (402). When the health lending component 113 in Figure 3 is performing the method, the input processor 300 may perform this processing. The information about the payor may be used in the method to create a payor Bayes graph (404). When the health lending component 113 in Figure 3 is performing the method, the graph model engine 302 may create this Bayes graph. The Bayes graph for the payor may also exchange data with a generated provider Bayes graph.
For a provider entity, the method may process provider information (examples of which are set forth above) via an API (406). When the health lending component 113 in Figure 3 is performing the method, the input processor 300 may perform this processing.
The information about the provider may be used in the method to create a provider Bayes graph (408). When the health lending component 113 in Figure 3 is performing the method, the graph model engine 302 may create this Bayes graph. The provider Bayes graph may also exchange data with the payer Bayes Graph.
For a consumer entity, the method may process consumer information (examples of which are set forth above) (410). When the health lending component 113 in Figure 3 is performing the
Thus, for each of the above entities, the health lending system may assess or predict the risk associated with the transaction with each of the above entities. The risk prediction may be a mixture of the three scores based on a probability model.
Figure 4 illustrates a method 400 for predicting risk for each of the different entities that may be performed, in one embodiment, by the health lending system 113 shown in Figures 2-3.
The method illustrated in Figure 4 also may be performed by software that is a plurality of lines of computer code that may be executed by a processor of the one or more computing resources so that the processor is configured to perform the operations and functions of the risk prediction as described below. In other embodiments, the method may be performed using hardware such as a programmed logic device, a programmed processor, a microcontroller, an application specific integrated circuit and the like.
As shown in Figure 4, the method may receive, for a payor, information for the risk prediction based on processing claims and benefits (examples of which are set forth above) via ETL (402). When the health lending component 113 in Figure 3 is performing the method, the input processor 300 may perform this processing. The information about the payor may be used in the method to create a payor Bayes graph (404). When the health lending component 113 in Figure 3 is performing the method, the graph model engine 302 may create this Bayes graph. The Bayes graph for the payor may also exchange data with a generated provider Bayes graph.
For a provider entity, the method may process provider information (examples of which are set forth above) via an API (406). When the health lending component 113 in Figure 3 is performing the method, the input processor 300 may perform this processing.
The information about the provider may be used in the method to create a provider Bayes graph (408). When the health lending component 113 in Figure 3 is performing the method, the graph model engine 302 may create this Bayes graph. The provider Bayes graph may also exchange data with the payer Bayes Graph.
For a consumer entity, the method may process consumer information (examples of which are set forth above) (410). When the health lending component 113 in Figure 3 is performing the
-10-method, the input processor 300 may perform this processing. The information about the consumer (and the claims and benefits information from the ETL) may be used in the method to create a consumer Bayes graph (412). When the health lending component 113 in Figure 3 is performing the method, the graph model engine 302 may create this Bayes graph.
As shown, one or more of the created Bayes graphs may be used in the method to create a health credit risk score ranking (414). When the health lending component 113 in Figure 3 is performing the method, the health credit score generator 304 may generate the score(s). An example of this method is described below starting at Figure 9. Thus, the method generates one or more health credit risk score(s) that may be used by the health lending system to assess the risk of the health services related lending described above.
In the above method, a Bayesian network classifiers is used that provides the capacity of giving a clear insight into the structural relationships in the domain under investigation. In addition, as of late, Bayesian network classifiers have had success for financial credit scoring. In the method, a BeliefNetwork or a network of Bayes Nets which is also called a Probabilistic Graph Model (PGM) may be used.
The method uses probabilistic graphs for modeling and assessment of credit concentration risk based on health and medical behaviors as a function of the risk. The destructive power of credit concentrations essentially depends on the amount of correlation among borrowers.
However, borrower company's correlation and concentration of credit risk exposures have been difficult for the banking industry to measure in an objective way as they are riddled with uncertainty. As a result, banks do not manage to make a quantitative link to the correlation driving risks and fail to prevent concentrations from accumulating. However, since the health lending system and method has the ability to exact health and medical behaviors tied to the consumer, the method creates BeliefNetworks that provide an attractive solution to the usual credit scoring problems, specifically within the health domain to show how to apply them in representing, quantifying and managing the uncertain knowledge in concentration of "health credits risk exposures".
The method may use a stepwise Belief network model building scheme and the method may incorporate prior beliefs regarding the risk exposure of a group of related behavior such as office revisits and outcomes and then update these beliefs through the whole model with the new
As shown, one or more of the created Bayes graphs may be used in the method to create a health credit risk score ranking (414). When the health lending component 113 in Figure 3 is performing the method, the health credit score generator 304 may generate the score(s). An example of this method is described below starting at Figure 9. Thus, the method generates one or more health credit risk score(s) that may be used by the health lending system to assess the risk of the health services related lending described above.
In the above method, a Bayesian network classifiers is used that provides the capacity of giving a clear insight into the structural relationships in the domain under investigation. In addition, as of late, Bayesian network classifiers have had success for financial credit scoring. In the method, a BeliefNetwork or a network of Bayes Nets which is also called a Probabilistic Graph Model (PGM) may be used.
The method uses probabilistic graphs for modeling and assessment of credit concentration risk based on health and medical behaviors as a function of the risk. The destructive power of credit concentrations essentially depends on the amount of correlation among borrowers.
However, borrower company's correlation and concentration of credit risk exposures have been difficult for the banking industry to measure in an objective way as they are riddled with uncertainty. As a result, banks do not manage to make a quantitative link to the correlation driving risks and fail to prevent concentrations from accumulating. However, since the health lending system and method has the ability to exact health and medical behaviors tied to the consumer, the method creates BeliefNetworks that provide an attractive solution to the usual credit scoring problems, specifically within the health domain to show how to apply them in representing, quantifying and managing the uncertain knowledge in concentration of "health credits risk exposures".
The method may use a stepwise Belief network model building scheme and the method may incorporate prior beliefs regarding the risk exposure of a group of related behavior such as office revisits and outcomes and then update these beliefs through the whole model with the new
-11-information as it is learned. The method may use a specific graph structure, BeliefNetwork network, and the model provides better understanding of the concentration risk accumulating due to strong direct or indirect business links between borrowers and lenders as a function of the health data that is used. The method also may use three model BeliefNetworks and the mutual information and construct a BeliefNetwork that is a reliable model that can be implemented to identify and control threat from concentration of credit exposures.
A Bayesian network (BN) represents a joint probability distribution over a set of discrete attributes. It is to be considered as a probabilistic white-box model consisting of a qualitative part specifying the conditional (inter)dependencies between the attributes and a quantitative part specifying the conditional probabilities of the data set attributes. Formally, a Bayesian network consists of two parts, OWS600, wherein a directed acyclic graph G consisting of nodes and arcs and one or more conditional probability tables itiNattUanit The nodes are the attribute whereas the arcs indicate direct dependencies. The Bayesian network is essentially a statistical model that makes it feasible to compute the (joint) posterior probability distribution of any subset of unobserved stochastic variables, given that the variables in the complementary subset are observed.
The graph G then encodes the independence relationships of the domain. The network B
represents the following joint probability distribution:
(Equation 1) This yields a Bayesian probabilistic graph structure that is familiar to those trained in the art.
Given this basic functionality, a baseline for discreet tractable variables is created where inference is exact. In our cases of the three probabilistic graph models (as shown in Figure 4), we have three tractable inference models.
In order to improve the performance of the models and graphs, for continuous variables such as pricing information, the method may utilize Markov chain Monte Carlo (MCMC
hereafter) which samples directly from the posterior distributions. The method may also use the well known Metropolis-Hastings algorithm for Markov Chains. The Metropolis-Hastings algorithm was first adapted for structural learning of Bayesian and Markov Networks by Madigan
A Bayesian network (BN) represents a joint probability distribution over a set of discrete attributes. It is to be considered as a probabilistic white-box model consisting of a qualitative part specifying the conditional (inter)dependencies between the attributes and a quantitative part specifying the conditional probabilities of the data set attributes. Formally, a Bayesian network consists of two parts, OWS600, wherein a directed acyclic graph G consisting of nodes and arcs and one or more conditional probability tables itiNattUanit The nodes are the attribute whereas the arcs indicate direct dependencies. The Bayesian network is essentially a statistical model that makes it feasible to compute the (joint) posterior probability distribution of any subset of unobserved stochastic variables, given that the variables in the complementary subset are observed.
The graph G then encodes the independence relationships of the domain. The network B
represents the following joint probability distribution:
(Equation 1) This yields a Bayesian probabilistic graph structure that is familiar to those trained in the art.
Given this basic functionality, a baseline for discreet tractable variables is created where inference is exact. In our cases of the three probabilistic graph models (as shown in Figure 4), we have three tractable inference models.
In order to improve the performance of the models and graphs, for continuous variables such as pricing information, the method may utilize Markov chain Monte Carlo (MCMC
hereafter) which samples directly from the posterior distributions. The method may also use the well known Metropolis-Hastings algorithm for Markov Chains. The Metropolis-Hastings algorithm was first adapted for structural learning of Bayesian and Markov Networks by Madigan
-12-and York. In the method; metropolis-Hastings and other MCMC algorithms are generally used for sampling from multi-dimensional distributions, especially when the number of dimensions is high. In our case of the Health Credit Score Models described above, the models are considered high dimensionality.
The BeliefNetworks building process for the provider network model and build process may use the following code example:
provider_bayes_net =
build_bayes_belief nett work( prob_procedures_performed_by_specialty count, prok_procedures_performed count, pro bpro vider_procedure_experience, prob_provider_age, prob_provider_experience, prob_provider_revoked_lieense, prok_providerAbility, prob_claim_line_edited_to_zero, prob_good_payer_price_data, prob_pdpayment.__payer_paiddifference, prob Joss, domains-dict( proceduresperformedbyspecialty_e ount=variable range bins, procedure s_performed_co tint ...variable_range_bin s, provider_procedure_experience-variable_range_bins, pro vider_age=[veryold', Ok1, middIeage, 'young], provider_experience-variable_range_bins, provider revoked license=boolean variable vals, provider_ability-variable_range_bins, claim_line_edited_to_zero=boolean_variab le_vals,
The BeliefNetworks building process for the provider network model and build process may use the following code example:
provider_bayes_net =
build_bayes_belief nett work( prob_procedures_performed_by_specialty count, prok_procedures_performed count, pro bpro vider_procedure_experience, prob_provider_age, prob_provider_experience, prob_provider_revoked_lieense, prok_providerAbility, prob_claim_line_edited_to_zero, prob_good_payer_price_data, prob_pdpayment.__payer_paiddifference, prob Joss, domains-dict( proceduresperformedbyspecialty_e ount=variable range bins, procedure s_performed_co tint ...variable_range_bin s, provider_procedure_experience-variable_range_bins, pro vider_age=[veryold', Ok1, middIeage, 'young], provider_experience-variable_range_bins, provider revoked license=boolean variable vals, provider_ability-variable_range_bins, claim_line_edited_to_zero=boolean_variab le_vals,
-13-good_sayer_price_data=boolean_variable_vals, pd_papnentpayerpaiddifferenee=variablerange_bins, loss...boolean_variable_yais )) return provider_bayes_net An example of the provider payer risk Bayes network in shown in Figure 5. As shown in Figure 5, the various information for a provider risk assessment are shown.
Figure 6 shows an example of a method 600 for a provider Bayes model generation starting with a procedure bundle for each health procedure wherein each procedure may be a single CPT code. A
typical medical/health procedure usually consists of more than one billing procedure code (CPT code).
The method calculates a PDHICO score for each line item (CPT code) and then combines them into an overall procedure bundle score. The method may use the patient data, payer data and/or provider data to generate a procedure risk assessment 602 for each of the procedures. Based on the risk assessment of each of the procedures, the method may determine a procedure bundle risk assessment score 604. Based on the procedure bundle risk assessment score, the health lending system may determine (606) whether or not to immediately reimburse the provider that may depend in part on a lender risk toleration.
Figure 7 illustrates an example of a method 700 for consumer risk modeling in which information about the consumer (702) is used. When the health lending component 113 in Figure 3 is performing the method, the graph model engine 302 may perform the method.
The information about the consumer may include a FICO credit score, financial data, wearable device data, health record data and insurance plan data. The information about the consumer may be used to make a consumer lending assessment (704). The consumer lending assessment 704 may be combined with data about a bank/lender (706) to determine (708) whether to lend money to the patient for the procedure. The determination about lending the money may also depend on the lender risk tolerance (710).
Figure 8 illustrates an example of the output of the BeliefNetwork graph inference model that shows the calculated probabilities that ultimately result in a probability of loss if the lending is made to a particular consumer.
Figure 6 shows an example of a method 600 for a provider Bayes model generation starting with a procedure bundle for each health procedure wherein each procedure may be a single CPT code. A
typical medical/health procedure usually consists of more than one billing procedure code (CPT code).
The method calculates a PDHICO score for each line item (CPT code) and then combines them into an overall procedure bundle score. The method may use the patient data, payer data and/or provider data to generate a procedure risk assessment 602 for each of the procedures. Based on the risk assessment of each of the procedures, the method may determine a procedure bundle risk assessment score 604. Based on the procedure bundle risk assessment score, the health lending system may determine (606) whether or not to immediately reimburse the provider that may depend in part on a lender risk toleration.
Figure 7 illustrates an example of a method 700 for consumer risk modeling in which information about the consumer (702) is used. When the health lending component 113 in Figure 3 is performing the method, the graph model engine 302 may perform the method.
The information about the consumer may include a FICO credit score, financial data, wearable device data, health record data and insurance plan data. The information about the consumer may be used to make a consumer lending assessment (704). The consumer lending assessment 704 may be combined with data about a bank/lender (706) to determine (708) whether to lend money to the patient for the procedure. The determination about lending the money may also depend on the lender risk tolerance (710).
Figure 8 illustrates an example of the output of the BeliefNetwork graph inference model that shows the calculated probabilities that ultimately result in a probability of loss if the lending is made to a particular consumer.
-14-Figure 9 illustrates an example of a PDHICO Provider/Payer example input data for the risk assessment. Thus, Figure 9 shows exemplary input data including a reimbursed price, reimbursed price stats and procedures performed by the provider. Figure 10 illustrates an example of a risk graph for the PDHICO Provider/Payer example data in Figure 9 generated by the system and method described above. As shown in Figure 10, various values for the example data in Figure 9 are generated and placed into the risk graph. For example, the probability of loss, P(loss), is calculated as 0.701 as shown in Figure 10. The probability of loss may be calculated using the methodology described above and using equation (1). The method may use the probabilities encoded in the graphical model to calculate the conditional probability P(loss=Truelprocedures_performed_by specialty_count="high", payment_average_payer_paid_amount_difference="medium"). This is where the representational efficiency of the graphical model comes into play as the conditional probability table for the resulting equation has more than 177, 147 terms. Figure 11 illustrates an example of the output of the system for the PDHICO Provider/Payer example data in Figure 9 including the scores generated by the system. In one embodiment, the risk score may be calculated as (1-P(loss) *
100). Then, from the example data in Figure 9, the system generates a risk score of 30 calculated as (1-0.7)*100) from the value calculated in Figure 9.
Figure 12 illustrates an example of a PDHICO Consumer example input data for the risk assessment in which various particulars about the consumer including health details and fmancial details are stored. In one embodiment, the consumer risk may be calculated as 0.63 based on the consumer input data. Figure 13 illustrates an example of a risk graph for the PDHICO consumer example data in Figure 12 generated by the system and method described above.
As shown in Figure 13, various values for the example data in Figure 12 are generated and placed into the risk graph. For example, the probability of loss, P(loss), is calculated as 0.37 as shown in Figure 13.
The probability of loss may be calculated using the methodology described above and using equation (1). The method may use the probabilities encoded in the graphical model to calculate the conditional probability P(loss=Truelconsumer_bmi="overweight", consumer_gender="male", smoker="false", consumer_age="40-69", debt_ratio="30-35", fico="700-749") This is where the representational efficiency of the graphical model comes into play as the conditional probability table for the resulting equation has more than 43,046,72 lterms. Figure 14 illustrates an example
100). Then, from the example data in Figure 9, the system generates a risk score of 30 calculated as (1-0.7)*100) from the value calculated in Figure 9.
Figure 12 illustrates an example of a PDHICO Consumer example input data for the risk assessment in which various particulars about the consumer including health details and fmancial details are stored. In one embodiment, the consumer risk may be calculated as 0.63 based on the consumer input data. Figure 13 illustrates an example of a risk graph for the PDHICO consumer example data in Figure 12 generated by the system and method described above.
As shown in Figure 13, various values for the example data in Figure 12 are generated and placed into the risk graph. For example, the probability of loss, P(loss), is calculated as 0.37 as shown in Figure 13.
The probability of loss may be calculated using the methodology described above and using equation (1). The method may use the probabilities encoded in the graphical model to calculate the conditional probability P(loss=Truelconsumer_bmi="overweight", consumer_gender="male", smoker="false", consumer_age="40-69", debt_ratio="30-35", fico="700-749") This is where the representational efficiency of the graphical model comes into play as the conditional probability table for the resulting equation has more than 43,046,72 lterms. Figure 14 illustrates an example
-15-of the output of the system for the PDHICO consumer example data in Figure 12 including the scores generated by the system. In one embodiment, the risk score may be calculated as (1-P(loss) * 100). Then, from the example data in Figure 12, the system generates a risk score of 63 calculated as (1-0.37)*100) from the value calculated in Figure 12.
The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limit the disclosure to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The embodiments were chosen and described in order to best explain the principles of the disclosure and its practical applications, to thereby enable others skilled in the art to best utilize the disclosure and various embodiments with various modifications as are suited to the particular use contemplated.
The system and method disclosed herein may be implemented via one or more components, systems, servers, appliances, other subcomponents, or distributed between such elements. When implemented as a system, such systems may include an/or involve, inter alia, components such as software modules, general-purpose CPU, RAM, etc. found in general-purpose computers. In implementations where the innovations reside on a server, such a server may include or involve components such as CPU, RAM, etc., such as those found in general-purpose computers.
Additionally, the system and method herein may be achieved via implementations with disparate or entirely different software, hardware and/or firmware components, beyond that set forth above. With regard to such other components (e.g., software, processing components, etc.) and/or computer-readable media associated with or embodying the present inventions, for example, aspects of the innovations herein may be implemented consistent with numerous general purpose or special purpose computing systems or configurations. Various exemplary computing systems, environments, and/or configurations that may be suitable for use with the innovations herein may include, but are not limited to: software or other components within or embodied on personal computers, servers or server computing devices such as routing/connectivity components, hand-held or laptop devices, multiprocessor systems, microprocessor-based systems, set top boxes, consumer electronic devices, network PCs, other existing computer platforms,
The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limit the disclosure to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The embodiments were chosen and described in order to best explain the principles of the disclosure and its practical applications, to thereby enable others skilled in the art to best utilize the disclosure and various embodiments with various modifications as are suited to the particular use contemplated.
The system and method disclosed herein may be implemented via one or more components, systems, servers, appliances, other subcomponents, or distributed between such elements. When implemented as a system, such systems may include an/or involve, inter alia, components such as software modules, general-purpose CPU, RAM, etc. found in general-purpose computers. In implementations where the innovations reside on a server, such a server may include or involve components such as CPU, RAM, etc., such as those found in general-purpose computers.
Additionally, the system and method herein may be achieved via implementations with disparate or entirely different software, hardware and/or firmware components, beyond that set forth above. With regard to such other components (e.g., software, processing components, etc.) and/or computer-readable media associated with or embodying the present inventions, for example, aspects of the innovations herein may be implemented consistent with numerous general purpose or special purpose computing systems or configurations. Various exemplary computing systems, environments, and/or configurations that may be suitable for use with the innovations herein may include, but are not limited to: software or other components within or embodied on personal computers, servers or server computing devices such as routing/connectivity components, hand-held or laptop devices, multiprocessor systems, microprocessor-based systems, set top boxes, consumer electronic devices, network PCs, other existing computer platforms,
-16-distributed computing environments that include one or more of the above systems or devices, etc.
In some instances, aspects of the system and method may be achieved via or performed by logic and/or logic instructions including program modules, executed in association with such components or circuitry, for example. In general, program modules may include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular instructions herein. The inventions may also be practiced in the context of distributed software, computer, or circuit settings where circuitry is connected via communication buses, circuitry or links. In distributed settings, control/instructions may occur from both local and remote computer storage media including memory storage devices.
The software, circuitry and components herein may also include and/or utilize one or more type of computer readable media. Computer readable media can be any available media that is resident on, associable with, or can be accessed by such circuits and/or computing components.
By way of example, and not limitation, computer readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and can accessed by computing component. Communication media may comprise computer readable instructions, data structures, program modules and/or other components. Further, communication media may include wired media such as a wired network or direct-wired connection, however no media of any such type herein includes transitory media. Combinations of the any of the above are also included within the scope of computer readable media.
In the present description, the terms component, module, device, etc. may refer to any type of logical or functional software elements, circuits, blocks and/or processes that may be implemented in a variety of ways. For example, the functions of various circuits and/or blocks can be combined with one another into any other number of modules. Each module may even be
In some instances, aspects of the system and method may be achieved via or performed by logic and/or logic instructions including program modules, executed in association with such components or circuitry, for example. In general, program modules may include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular instructions herein. The inventions may also be practiced in the context of distributed software, computer, or circuit settings where circuitry is connected via communication buses, circuitry or links. In distributed settings, control/instructions may occur from both local and remote computer storage media including memory storage devices.
The software, circuitry and components herein may also include and/or utilize one or more type of computer readable media. Computer readable media can be any available media that is resident on, associable with, or can be accessed by such circuits and/or computing components.
By way of example, and not limitation, computer readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and can accessed by computing component. Communication media may comprise computer readable instructions, data structures, program modules and/or other components. Further, communication media may include wired media such as a wired network or direct-wired connection, however no media of any such type herein includes transitory media. Combinations of the any of the above are also included within the scope of computer readable media.
In the present description, the terms component, module, device, etc. may refer to any type of logical or functional software elements, circuits, blocks and/or processes that may be implemented in a variety of ways. For example, the functions of various circuits and/or blocks can be combined with one another into any other number of modules. Each module may even be
-17-implemented as a software program stored on a tangible memory (e.g., random access memory, read only memory, CD-ROM memory, hard disk drive, etc.) to be read by a central processing unit to implement the functions of the innovations herein. Or, the modules can comprise programming instructions transmitted to a general purpose computer or to processing/graphics hardware via a transmission carrier wave. Also, the modules can be implemented as hardware logic circuitry implementing the functions encompassed by the innovations herein. Finally, the modules can be implemented using special purpose instructions (SIMD
instructions), field programmable logic arrays or any mix thereof which provides the desired level performance and cost.
As disclosed herein, features consistent with the disclosure may be implemented via computer-hardware, software and/or firmware. For example, the systems and methods disclosed herein may be embodied in various forms including, for example, a data processor, such as a computer that also includes a database, digital electronic circuitry, firmware, software, or in combinations of them. Further, while some of the disclosed implementations describe specific hardware components, systems and methods consistent with the innovations herein may be implemented with any combination of hardware, software and/or firmware.
Moreover, the above-noted features and other aspects and principles of the innovations herein may be implemented in various environments. Such environments and related applications may be specially constructed for performing the various routines, processes and/or operations according to the invention or they may include a general-purpose computer or computing platform selectively activated or reconfigured by code to provide the necessary functionality. The processes disclosed herein are not inherently related to any particular computer, network, architecture, environment, or other apparatus, and may be implemented by a suitable combination of hardware, software, and/or firmware. For example, various general-purpose machines may be used with programs written in accordance with teachings of the invention, or it may be more convenient to construct a specialized apparatus or system to perform the required methods and techniques.
Aspects of the method and system described herein, such as the logic, may also be implemented as functionality programmed into any of a variety of circuitry, including programmable logic devices ("PLDs"), such as field programmable gate arrays ("FPGAs"), programmable array logic ("PAL") devices, electrically programmable logic and memory devices
instructions), field programmable logic arrays or any mix thereof which provides the desired level performance and cost.
As disclosed herein, features consistent with the disclosure may be implemented via computer-hardware, software and/or firmware. For example, the systems and methods disclosed herein may be embodied in various forms including, for example, a data processor, such as a computer that also includes a database, digital electronic circuitry, firmware, software, or in combinations of them. Further, while some of the disclosed implementations describe specific hardware components, systems and methods consistent with the innovations herein may be implemented with any combination of hardware, software and/or firmware.
Moreover, the above-noted features and other aspects and principles of the innovations herein may be implemented in various environments. Such environments and related applications may be specially constructed for performing the various routines, processes and/or operations according to the invention or they may include a general-purpose computer or computing platform selectively activated or reconfigured by code to provide the necessary functionality. The processes disclosed herein are not inherently related to any particular computer, network, architecture, environment, or other apparatus, and may be implemented by a suitable combination of hardware, software, and/or firmware. For example, various general-purpose machines may be used with programs written in accordance with teachings of the invention, or it may be more convenient to construct a specialized apparatus or system to perform the required methods and techniques.
Aspects of the method and system described herein, such as the logic, may also be implemented as functionality programmed into any of a variety of circuitry, including programmable logic devices ("PLDs"), such as field programmable gate arrays ("FPGAs"), programmable array logic ("PAL") devices, electrically programmable logic and memory devices
-18-and standard cell-based devices, as well as application specific integrated circuits. Some other possibilities for implementing aspects include: memory devices, microcontrollers with memory (such as EEPROM), embedded microprocessors, firmware, software, etc.
Furthermore, aspects may be embodied in microprocessors having software-based circuit emulation, discrete logic (sequential and combinatorial), custom devices, fuzzy (neural) logic, quantum devices, and hybrids of any of the above device types. The underlying device technologies may be provided in a variety of component types, e.g., metal-oxide semiconductor field-effect transistor ("MOSFET") technologies like complementary metal-oxide semiconductor ("CMOS"), bipolar technologies like emitter-coupled logic ("ECL"), polymer technologies (e.g., silicon-conjugated polymer and metal-conjugated polymer-metal structures), mixed analog and digital, and so on.
It should also be noted that the various logic and/or functions disclosed herein may be enabled using any number of combinations of hardware, firmware, and/or as data and/or instructions embodied in various machine-readable or computer-readable media, in terms of their behavioral, register transfer, logic component, and/or other characteristics.
Computer-readable media in which such formatted data and/or instructions may be embodied include, but are not limited to, non-volatile storage media in various forms (e.g., optical, magnetic or semiconductor storage media) though again does not include transitory media. Unless the context clearly requires otherwise, throughout the description, the words "comprise," "comprising," and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is to say, in a sense of "including, but not limited to." Words using the singular or plural number also include the plural or singular number respectively. Additionally, the words "herein,"
"hereunder,"
"above," "below," and words of similar import refer to this application as a whole and not to any particular portions of this application. When the word "or" is used in reference to a list of two or more items, that word covers all of the following interpretations of the word:
any of the items in the list, all of the items in the list and any combination of the items in the list.
Although certain presently preferred implementations of the invention have been specifically described herein, it will be apparent to those skilled in the art to which the invention pertains that variations and modifications of the various implementations shown and described herein may be made without departing from the spirit and scope of the invention. Accordingly, it is intended that the invention be limited only to the extent required by the applicable rules of law.
Furthermore, aspects may be embodied in microprocessors having software-based circuit emulation, discrete logic (sequential and combinatorial), custom devices, fuzzy (neural) logic, quantum devices, and hybrids of any of the above device types. The underlying device technologies may be provided in a variety of component types, e.g., metal-oxide semiconductor field-effect transistor ("MOSFET") technologies like complementary metal-oxide semiconductor ("CMOS"), bipolar technologies like emitter-coupled logic ("ECL"), polymer technologies (e.g., silicon-conjugated polymer and metal-conjugated polymer-metal structures), mixed analog and digital, and so on.
It should also be noted that the various logic and/or functions disclosed herein may be enabled using any number of combinations of hardware, firmware, and/or as data and/or instructions embodied in various machine-readable or computer-readable media, in terms of their behavioral, register transfer, logic component, and/or other characteristics.
Computer-readable media in which such formatted data and/or instructions may be embodied include, but are not limited to, non-volatile storage media in various forms (e.g., optical, magnetic or semiconductor storage media) though again does not include transitory media. Unless the context clearly requires otherwise, throughout the description, the words "comprise," "comprising," and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is to say, in a sense of "including, but not limited to." Words using the singular or plural number also include the plural or singular number respectively. Additionally, the words "herein,"
"hereunder,"
"above," "below," and words of similar import refer to this application as a whole and not to any particular portions of this application. When the word "or" is used in reference to a list of two or more items, that word covers all of the following interpretations of the word:
any of the items in the list, all of the items in the list and any combination of the items in the list.
Although certain presently preferred implementations of the invention have been specifically described herein, it will be apparent to those skilled in the art to which the invention pertains that variations and modifications of the various implementations shown and described herein may be made without departing from the spirit and scope of the invention. Accordingly, it is intended that the invention be limited only to the extent required by the applicable rules of law.
19 PCT/US2016/014117 While the foregoing has been with reference to a particular embodiment of the disclosure, it will be appreciated by those skilled in the art that changes in this embodiment may be made without departing from the principles and spirit of the disclosure, the scope of which is defined by the appended claims.
Claims (24)
1. A system, comprising:
a computer system having a processor and a memory;
the processor configured to receive data about a health service transaction;
and the processor configured to generate a risk measure for the health service transaction using the data about the health service transaction.
a computer system having a processor and a memory;
the processor configured to receive data about a health service transaction;
and the processor configured to generate a risk measure for the health service transaction using the data about the health service transaction.
2. The system of 1, wherein the processor is configured to use a probabilistic graph model to generate the risk measure.
3. The system of claim 2, wherein the processor is configured to generate a payor bayes graph, a provider bayes graph and a consumer bayes graph.
4. The system of claim 3, wherein the processor is configured to generate the risk measure by combining the payor bayes graph, the provider bayes graph and the consumer bayes graph.
5. The system of claim 2, wherein the processor is configured to use a stepwise belief network to generate the probabilistic graph model.
6. The system of claim 1, wherein the processor is configured to generate a risk score for an entity involved in the health service transaction.
7. The system of claim 6, wherein the entity is one of a health service consumer, a health service provider and a health service payer.
8. The system of claim 1, wherein the risk measure is a risk score.
9. A method, comprising:
receiving data about a health service transaction; and generating a risk measure for the health service transaction using the data about the health service transaction.
receiving data about a health service transaction; and generating a risk measure for the health service transaction using the data about the health service transaction.
10. The method of 9, wherein generating the risk measure further comprises using a probabilistic graph model to generate the risk measure.
11. The method of claim 10, wherein using the probabilistic graph model further comprises generating a payor bayes graph, generating a provider bayes graph and generating a consumer bayes graph.
12. The method of claim 11, wherein generating the risk measure further comprises combining the payor bayes graph, the provider bayes graph and the consumer bayes graph to generate the risk measure.
13. The method of claim 10, wherein using the probabilistic graph model further comprises using a stepwise belief network to generate the probabilistic graph model.
14. The method of claim 9 further comprising generating a risk score for an entity involved in the health service transaction.
15. The method of claim 14, wherein the entity is one of a health service consumer, a health service provider and a health service payer.
16. The method of claim 9, wherein the risk measure is a risk score.
17. An apparatus, comprising:
a processor;
a memory;
the processor configured to receive data about a health service transaction;
and the processor configured to generate a risk measure for the health service transaction using the data about the health service transaction.
a processor;
a memory;
the processor configured to receive data about a health service transaction;
and the processor configured to generate a risk measure for the health service transaction using the data about the health service transaction.
18. The apparatus of 17, wherein the processor is configured to use a probabilistic graph model to generate the risk measure.
19. The apparatus of claim 18, wherein the processor is configured to generate a payor bayes graph, a provider bayes graph and a consumer bayes graph.
20. The apparatus of claim 19, wherein the processor is configured to generate the risk measure by combining the payor bayes graph, the provider bayes graph and the consumer bayes graph.
21. The apparatus of claim 18, wherein the processor is configured to use a stepwise belief network to generate the probabilistic graph model.
22. The apparatus of claim 17, wherein the processor is configured to generate a risk score for an entity involved in the health service transaction.
23. The apparatus of claim 22, wherein the entity is one of a health service consumer, a health service provider and a health service payer.
24. The apparatus of claim 17, wherein the risk measure is a risk score.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US201562105503P | 2015-01-20 | 2015-01-20 | |
| US62/105,503 | 2015-01-20 | ||
| PCT/US2016/014117 WO2016118619A1 (en) | 2015-01-20 | 2016-01-20 | Health lending system and method using probabilistic graph models |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CA2985839A1 true CA2985839A1 (en) | 2016-07-28 |
Family
ID=56408058
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA2985839A Abandoned CA2985839A1 (en) | 2015-01-20 | 2016-01-20 | Health lending system and method using probabilistic graph models |
Country Status (7)
| Country | Link |
|---|---|
| US (1) | US10417379B2 (en) |
| EP (1) | EP3248167A4 (en) |
| JP (1) | JP2018506786A (en) |
| CN (1) | CN107615326A (en) |
| CA (1) | CA2985839A1 (en) |
| HK (1) | HK1249957A1 (en) |
| WO (1) | WO2016118619A1 (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11062802B1 (en) | 2015-06-04 | 2021-07-13 | Cerner Innovation, Inc. | Medical resource forecasting |
| US10565351B2 (en) * | 2015-08-24 | 2020-02-18 | 3M Innovative Properties Company | Analysis and rule generation of medical documents |
| US10776878B1 (en) | 2017-06-29 | 2020-09-15 | State Farm Mutual Automobile Insurance Company | Social media data aggregation to optimize underwriting |
| CN109598414B (en) * | 2018-11-13 | 2023-04-21 | 创新先进技术有限公司 | Risk assessment model training, risk assessment method and device and electronic equipment |
| CN109993538A (en) * | 2019-02-28 | 2019-07-09 | 同济大学 | Identity theft detection method based on probability graph model |
| US11586826B2 (en) * | 2020-10-01 | 2023-02-21 | Crowdsmart, Inc. | Managing and measuring semantic coverage in knowledge discovery processes |
| US12052183B1 (en) | 2023-03-15 | 2024-07-30 | Wells Fargo Bank, N.A. | Resource allocation discovery and optimization service |
Family Cites Families (126)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2738289B2 (en) | 1993-12-30 | 1998-04-08 | 日本電気株式会社 | Manufacturing method of liquid crystal display device |
| US5835897C1 (en) | 1995-06-22 | 2002-02-19 | Symmetry Health Data Systems | Computer-implemented method for profiling medical claims |
| US6279041B1 (en) | 1998-11-13 | 2001-08-21 | International Business Machines Corporation | Methods, systems and computer program products for differencing data communications using a message queue |
| US20020022973A1 (en) | 2000-03-24 | 2002-02-21 | Jianguo Sun | Medical information management system and patient interface appliance |
| US20020038233A1 (en) | 2000-06-09 | 2002-03-28 | Dmitry Shubov | System and method for matching professional service providers with consumers |
| US20040143446A1 (en) | 2001-03-20 | 2004-07-22 | David Lawrence | Long term care risk management clearinghouse |
| AU2002355575A1 (en) | 2001-08-08 | 2003-02-24 | Trivium Systems Inc. | Scalable messaging platform for the integration of business software components |
| AU2002363143A1 (en) | 2001-11-01 | 2003-05-12 | Medunite, Inc. | System and method for facilitating the exchange of health care transactional information |
| US7092956B2 (en) | 2001-11-02 | 2006-08-15 | General Electric Capital Corporation | Deduplication system |
| EP1481357A2 (en) | 2002-03-06 | 2004-12-01 | Siemens Medical Solutions Health Services Corporation | System and method for providing a generic health care data repository |
| US20040078211A1 (en) | 2002-03-18 | 2004-04-22 | Merck & Co., Inc. | Computer assisted and/or implemented process and system for managing and/or providing a medical information portal for healthcare providers |
| US7917378B2 (en) | 2002-04-09 | 2011-03-29 | Siemens Medical Solutions Usa, Inc. | System for processing healthcare claim data |
| EP1609044A4 (en) | 2003-03-28 | 2008-08-06 | Dun & Bradstreet Inc | System and method for data cleansing |
| US20050137912A1 (en) | 2003-03-31 | 2005-06-23 | Rao R. B. | Systems and methods for automated classification of health insurance claims to predict claim outcome |
| US20050010452A1 (en) | 2003-06-27 | 2005-01-13 | Lusen William D. | System and method for processing transaction records suitable for healthcare and other industries |
| US20050102170A1 (en) | 2003-09-09 | 2005-05-12 | Lefever David L. | System for processing transaction data |
| US20050071189A1 (en) | 2003-09-25 | 2005-03-31 | Blake Richard A. | System, method, and business method for storage, search and retrieval of clinical information |
| US8005687B1 (en) | 2003-10-15 | 2011-08-23 | Ingenix, Inc. | System, method and computer program product for estimating medical costs |
| US8108225B2 (en) | 2003-12-17 | 2012-01-31 | Joan Logue | Method, system, and software for analysis of a billing process |
| US7200604B2 (en) | 2004-02-17 | 2007-04-03 | Hewlett-Packard Development Company, L.P. | Data de-duplication |
| US20050222912A1 (en) | 2004-03-30 | 2005-10-06 | Chambers David E | System and method of processing commercial transactions through an internet website |
| US7386565B1 (en) | 2004-05-24 | 2008-06-10 | Sun Microsystems, Inc. | System and methods for aggregating data from multiple sources |
| US20070214133A1 (en) | 2004-06-23 | 2007-09-13 | Edo Liberty | Methods for filtering data and filling in missing data using nonlinear inference |
| US8364501B2 (en) | 2004-08-09 | 2013-01-29 | Epic Systems Corporation | Electronic appointment scheduling for medical resources |
| US20060036478A1 (en) | 2004-08-12 | 2006-02-16 | Vladimir Aleynikov | System, method and computer program for interactive voice recognition scheduler, reminder and messenger |
| US9471978B2 (en) | 2004-10-04 | 2016-10-18 | Banner Health | Methodologies linking patterns from multi-modality datasets |
| US20060089862A1 (en) | 2004-10-25 | 2006-04-27 | Sudhir Anandarao | System and method for modeling benefits |
| US7606762B1 (en) | 2004-11-05 | 2009-10-20 | Rdm Corporation | System and method for providing a distributed decisioning environment for processing of financial transactions |
| AU2005307823B2 (en) | 2004-11-16 | 2012-03-08 | Health Dialog Services Corporation | Systems and methods for predicting healthcare related risk events and financial risk |
| GB0427133D0 (en) | 2004-12-10 | 2005-01-12 | British Telecomm | Workflow scheduler |
| US7466316B1 (en) | 2004-12-14 | 2008-12-16 | Nvidia Corporation | Apparatus, system, and method for distributing work to integrated heterogeneous processors |
| US20060136264A1 (en) | 2004-12-21 | 2006-06-22 | Gh Global Health Direct, Llc | System and method for improved health care access |
| US8069060B2 (en) | 2004-12-23 | 2011-11-29 | Merge Healthcare Incorporated | System and method for managing medical facility procedures and records |
| US8620729B2 (en) | 2005-07-07 | 2013-12-31 | International Institute Of Information Technology | Methods for supply chain management incorporating uncertainty |
| US7665016B2 (en) | 2005-11-14 | 2010-02-16 | Sun Microsystems, Inc. | Method and apparatus for virtualized XML parsing |
| US20070118399A1 (en) | 2005-11-22 | 2007-05-24 | Avinash Gopal B | System and method for integrated learning and understanding of healthcare informatics |
| US20070156455A1 (en) | 2005-12-01 | 2007-07-05 | Tarino Michael D | System and Method for Providing a Consumer Healthcare Guide |
| CA2631756A1 (en) | 2005-12-01 | 2007-06-07 | Firestar Software, Inc. | System and method for exchanging information among exchange applications |
| US20070180451A1 (en) | 2005-12-30 | 2007-08-02 | Ryan Michael J | System and method for meta-scheduling |
| US20070260492A1 (en) | 2006-03-09 | 2007-11-08 | Microsoft Corporation | Master patient index |
| US20070233603A1 (en) | 2006-03-30 | 2007-10-04 | Schmidgall Matthew M | Flexible routing of electronic-based transactions |
| US8359298B2 (en) | 2006-04-03 | 2013-01-22 | International Business Machines Corporation | Method, system, and program product for managing adapter association for a data graph of data objects |
| US20080126264A1 (en) | 2006-05-02 | 2008-05-29 | Tellefsen Jens E | Systems and methods for price optimization using business segmentation |
| US7526486B2 (en) | 2006-05-22 | 2009-04-28 | Initiate Systems, Inc. | Method and system for indexing information about entities with respect to hierarchies |
| JP4863778B2 (en) * | 2006-06-07 | 2012-01-25 | ソニー株式会社 | Information processing apparatus, information processing method, and computer program |
| US7765146B2 (en) | 2006-06-09 | 2010-07-27 | Research Center For Prevention Of Diabetes | Method and system of adjusting medical cost through auction |
| US7885436B2 (en) | 2006-07-13 | 2011-02-08 | Authentec, Inc. | System for and method of assigning confidence values to fingerprint minutiae points |
| US20080082980A1 (en) | 2006-09-28 | 2008-04-03 | Edge Inova International, Inc. | System and method for using filters and standardized messages to identify and schedule appointments in aggregate resource scheduling applications |
| US7860786B2 (en) * | 2006-10-17 | 2010-12-28 | Canopy Acquisition, Llc | Predictive score for lending |
| JP4898405B2 (en) | 2006-12-01 | 2012-03-14 | キヤノン株式会社 | Document data processing method, document data creation device, and document data processing device |
| WO2008079325A1 (en) | 2006-12-22 | 2008-07-03 | Hartford Fire Insurance Company | System and method for utilizing interrelated computerized predictive models |
| US7917515B1 (en) | 2007-03-26 | 2011-03-29 | Lsi Corporation | System and method of accelerating processing of streaming data |
| US8103952B2 (en) | 2007-03-27 | 2012-01-24 | Konica Minolta Laboratory U.S.A., Inc. | Directed SAX parser for XML documents |
| US20080319983A1 (en) | 2007-04-20 | 2008-12-25 | Robert Meadows | Method and apparatus for identifying and resolving conflicting data records |
| US20080288292A1 (en) | 2007-05-15 | 2008-11-20 | Siemens Medical Solutions Usa, Inc. | System and Method for Large Scale Code Classification for Medical Patient Records |
| US8341623B2 (en) | 2007-05-22 | 2012-12-25 | International Business Machines Corporation | Integrated placement planning for heterogenous storage area network data centers |
| US7992153B2 (en) | 2007-05-30 | 2011-08-02 | Red Hat, Inc. | Queuing for thread pools using number of bytes |
| US8145644B2 (en) | 2007-07-31 | 2012-03-27 | Interfix, Llc | Systems and methods for providing access to medical information |
| US8826173B2 (en) | 2007-09-26 | 2014-09-02 | Siemens Aktiengesellschaft | Graphical interface for the management of sequential medical data |
| EP2058733A3 (en) | 2007-11-09 | 2009-09-02 | Avro Computing Inc. | Multi-tier interface for management of operational structured data |
| US7797205B2 (en) | 2007-12-21 | 2010-09-14 | Exxonmobil Research And Engineering Company | System for optimizing bulk product allocation, transportation and blending |
| US8171554B2 (en) | 2008-02-04 | 2012-05-01 | Yuval Elovici | System that provides early detection, alert, and response to electronic threats |
| TW200935418A (en) | 2008-02-05 | 2009-08-16 | Skymedi Corp | Semiconductor memory device |
| US8095975B2 (en) | 2008-03-18 | 2012-01-10 | International Business Machines Corporation | Dynamic document merging method and system |
| US8417755B1 (en) | 2008-05-28 | 2013-04-09 | Michael F. Zimmer | Systems and methods for reducing memory traffic and power consumption in a processing environment by solving a system of linear equations |
| US20090300054A1 (en) | 2008-05-29 | 2009-12-03 | Kathleen Fisher | System for inferring data structures |
| US8073801B1 (en) | 2008-05-30 | 2011-12-06 | The Decision Model Licensing, LLC | Business decision modeling and management system and method |
| US7668757B2 (en) | 2008-06-09 | 2010-02-23 | Weiwen Weng | Methods and system of contacting at least one service provider anonymously |
| US20090313045A1 (en) | 2008-06-11 | 2009-12-17 | Boyce Mark D | System and Method for Medical Research and Clinical Trial |
| US20100076950A1 (en) | 2008-09-10 | 2010-03-25 | Expanse Networks, Inc. | Masked Data Service Selection |
| US8260773B2 (en) | 2008-09-24 | 2012-09-04 | International Business Machines Corporation | Method for extracting signature from problem records through unstructured and structured text mapping, classification and ranking |
| US20100138243A1 (en) | 2008-10-02 | 2010-06-03 | Payformance Corporation | Systems and methods for facilitating healthcare cost remittance, adjudication, and reimbursement processes |
| US20100088108A1 (en) | 2008-10-08 | 2010-04-08 | Astrazeneca Ab | Pharmaceutical relational database |
| US20120130736A1 (en) | 2008-10-24 | 2012-05-24 | Obsidian Healthcare Disclosure Services, LLC | Systems and methods involving physician payment data |
| US8442931B2 (en) | 2008-12-01 | 2013-05-14 | The Boeing Company | Graph-based data search |
| US9141758B2 (en) | 2009-02-20 | 2015-09-22 | Ims Health Incorporated | System and method for encrypting provider identifiers on medical service claim transactions |
| US8250026B2 (en) | 2009-03-06 | 2012-08-21 | Peoplechart Corporation | Combining medical information captured in structured and unstructured data formats for use or display in a user application, interface, or view |
| US8286191B2 (en) | 2009-05-14 | 2012-10-09 | International Business Machines Corporation | Dynamically composing data stream processing applications |
| US20100295674A1 (en) | 2009-05-21 | 2010-11-25 | Silverplus, Inc. | Integrated health management console |
| US8103667B2 (en) | 2009-05-28 | 2012-01-24 | Microsoft Corporation | Ranking results of multiple intent queries |
| AU2010266073A1 (en) | 2009-06-24 | 2012-01-19 | Exxonmobil Research And Engineering Company | Tools for assisting in petroleum product transportation logistics |
| US8731965B2 (en) | 2009-07-19 | 2014-05-20 | Poonam Erry | Collaborative multi-facility medication management system |
| WO2011032086A2 (en) | 2009-09-14 | 2011-03-17 | Ii4Sm - International Institute For The Safety Of Medicines Ltd. | Semantic interoperability system for medicinal information |
| US8775286B2 (en) | 2009-09-23 | 2014-07-08 | Sap Ag | System and method for management of financial products portfolio using centralized price and performance optimization tool |
| US11562323B2 (en) * | 2009-10-01 | 2023-01-24 | DecisionQ Corporation | Application of bayesian networks to patient screening and treatment |
| US8521555B2 (en) * | 2009-12-09 | 2013-08-27 | Hartford Fire Insurance Company | System and method using a predictive model for nurse intervention program decisions |
| US8650317B2 (en) | 2009-12-17 | 2014-02-11 | American Express Travel Related Services Company, Inc. | System and method for searching channels based on channel rating |
| US8363662B2 (en) | 2010-03-19 | 2013-01-29 | Cisco Technology, Inc. | Alternate down paths for directed acyclic graph (DAG) routing |
| US20130085769A1 (en) * | 2010-03-31 | 2013-04-04 | Risk Management Solutions Llc | Characterizing healthcare provider, claim, beneficiary and healthcare merchant normal behavior using non-parametric statistical outlier detection scoring techniques |
| US8326869B2 (en) | 2010-09-23 | 2012-12-04 | Accenture Global Services Limited | Analysis of object structures such as benefits and provider contracts |
| US8515777B1 (en) | 2010-10-13 | 2013-08-20 | ProcessProxy Corporation | System and method for efficient provision of healthcare |
| US8495108B2 (en) | 2010-11-30 | 2013-07-23 | International Business Machines Corporation | Virtual node subpool management |
| US20120158429A1 (en) | 2010-12-20 | 2012-06-21 | David Phillip Murawski | Medical service broker systems and methods |
| US9846850B2 (en) | 2010-12-30 | 2017-12-19 | Cerner Innovation, Inc. | Consolidation of healthcare-related schedules across disparate systems |
| US20120239417A1 (en) | 2011-03-04 | 2012-09-20 | Pourfallah Stacy S | Healthcare wallet payment processing apparatuses, methods and systems |
| US20120245958A1 (en) | 2011-03-25 | 2012-09-27 | Surgichart, Llc | Case-Centric Medical Records System with Social Networking |
| US20120290320A1 (en) | 2011-05-13 | 2012-11-15 | Kurgan Michael J | System for leveraging social and restricted availability content in clinical processes, and a method thereof |
| US8984464B1 (en) | 2011-11-21 | 2015-03-17 | Tabula, Inc. | Detailed placement with search and repair |
| US20130138554A1 (en) * | 2011-11-30 | 2013-05-30 | Rawllin International Inc. | Dynamic risk assessment and credit standards generation |
| US8943059B2 (en) | 2011-12-21 | 2015-01-27 | Sap Se | Systems and methods for merging source records in accordance with survivorship rules |
| US10490304B2 (en) | 2012-01-26 | 2019-11-26 | Netspective Communications Llc | Device-driven non-intermediated blockchain system over a social integrity network |
| US11310324B2 (en) | 2012-02-03 | 2022-04-19 | Twitter, Inc. | System and method for determining relevance of social content |
| US9027024B2 (en) | 2012-05-09 | 2015-05-05 | Rackspace Us, Inc. | Market-based virtual machine allocation |
| KR101860811B1 (en) | 2012-08-23 | 2018-05-24 | 인터디지탈 패튼 홀딩스, 인크 | Operating with multiple schedulers in a wireless system |
| US8959119B2 (en) | 2012-08-27 | 2015-02-17 | International Business Machines Corporation | Context-based graph-relational intersect derived database |
| US20140081652A1 (en) * | 2012-09-14 | 2014-03-20 | Risk Management Solutions Llc | Automated Healthcare Risk Management System Utilizing Real-time Predictive Models, Risk Adjusted Provider Cost Index, Edit Analytics, Strategy Management, Managed Learning Environment, Contact Management, Forensic GUI, Case Management And Reporting System For Preventing And Detecting Healthcare Fraud, Abuse, Waste And Errors |
| US20140088981A1 (en) | 2012-09-21 | 2014-03-27 | Medimpact Healthcare Systems, Inc. | Systems and methods for proactive identification of formulary change impacts |
| US20140136233A1 (en) | 2012-11-14 | 2014-05-15 | William Atkinson | Managing Personal Health Record Information about Doctor-Patient Communication, Care interactions, health metrics ,customer vendor relationship management platforms, and personal health history in a GLOBAL PERSONAL HEALTH RECORD TIMELINE integrated within an (ERP/EMRSE) ENTERPRISE RESOURCE PLANNING ELECTRONIC MEDICAL RECORD SOFTWARE ENVIRONMENT localized medical data ecosystem |
| US20140222482A1 (en) | 2013-02-05 | 2014-08-07 | Wal-Mart Stores, Inc. | Online appointment schedulers |
| US9129046B2 (en) | 2013-02-25 | 2015-09-08 | 4medica, Inc. | Systems and methods for managing a master patient index including duplicate record detection |
| US8670996B1 (en) | 2013-03-14 | 2014-03-11 | David I. Weiss | Health care incentive apparatus and method |
| US20140358578A1 (en) | 2013-05-31 | 2014-12-04 | American Pharmacotherapy, Llc | System and method for comparing pharmaceutical prices and medication utilization |
| US9460188B2 (en) | 2013-06-03 | 2016-10-04 | Bank Of America Corporation | Data warehouse compatibility |
| US20150095068A1 (en) | 2013-10-01 | 2015-04-02 | Cerner Innovation, Inc. | Population health management systems and methods for clinical and operational programs |
| US9704208B2 (en) | 2013-10-22 | 2017-07-11 | ZocDoc, Inc. | System and method for accessing healthcare appointments from multiple disparate sources |
| US10720233B2 (en) | 2013-11-20 | 2020-07-21 | Medical Informatics Corp. | Web-enabled disease-specific monitoring |
| US11126627B2 (en) | 2014-01-14 | 2021-09-21 | Change Healthcare Holdings, Llc | System and method for dynamic transactional data streaming |
| US10340038B2 (en) | 2014-05-13 | 2019-07-02 | Nant Holdings Ip, Llc | Healthcare transaction validation via blockchain, systems and methods |
| US9208284B1 (en) | 2014-06-27 | 2015-12-08 | Practice Fusion, Inc. | Medical professional application integration into electronic health record system |
| US9608829B2 (en) | 2014-07-25 | 2017-03-28 | Blockchain Technologies Corporation | System and method for creating a multi-branched blockchain with configurable protocol rules |
| US9507824B2 (en) | 2014-08-22 | 2016-11-29 | Attivio Inc. | Automated creation of join graphs for unrelated data sets among relational databases |
| US11328307B2 (en) | 2015-02-24 | 2022-05-10 | OpSec Online, Ltd. | Brand abuse monitoring system with infringement detection engine and graphical user interface |
| US10572796B2 (en) | 2015-05-06 | 2020-02-25 | Saudi Arabian Oil Company | Automated safety KPI enhancement |
| US10269012B2 (en) | 2015-11-06 | 2019-04-23 | Swfl, Inc. | Systems and methods for secure and private communications |
| US10102340B2 (en) | 2016-06-06 | 2018-10-16 | PokitDok, Inc. | System and method for dynamic healthcare insurance claims decision support |
| US10108954B2 (en) | 2016-06-24 | 2018-10-23 | PokitDok, Inc. | System and method for cryptographically verified data driven contracts |
-
2016
- 2016-01-20 EP EP16740673.5A patent/EP3248167A4/en not_active Withdrawn
- 2016-01-20 JP JP2017538328A patent/JP2018506786A/en active Pending
- 2016-01-20 US US15/001,703 patent/US10417379B2/en active Active
- 2016-01-20 CA CA2985839A patent/CA2985839A1/en not_active Abandoned
- 2016-01-20 CN CN201680016928.6A patent/CN107615326A/en active Pending
- 2016-01-20 WO PCT/US2016/014117 patent/WO2016118619A1/en active Application Filing
-
2018
- 2018-07-19 HK HK18109342.6A patent/HK1249957A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| US10417379B2 (en) | 2019-09-17 |
| WO2016118619A1 (en) | 2016-07-28 |
| CN107615326A (en) | 2018-01-19 |
| US20160210423A1 (en) | 2016-07-21 |
| JP2018506786A (en) | 2018-03-08 |
| EP3248167A1 (en) | 2017-11-29 |
| EP3248167A4 (en) | 2018-08-08 |
| HK1249957A1 (en) | 2018-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10417379B2 (en) | Health lending system and method using probabilistic graph models | |
| Sohaib et al. | A PLS-SEM neural network approach for understanding cryptocurrency adoption | |
| US20210357029A1 (en) | Ai solution selection for an automated robotic process | |
| BR112019025671A2 (en) | system and method for granting a loan to a consumer determined to be a good payer | |
| US11226994B2 (en) | Modifying data structures to indicate derived relationships among entity data objects | |
| AU2023314124A1 (en) | Systems and methods for providing process automation and artificial intelligence, market aggregation, and embedded marketplaces for a transactions platform | |
| US20200387990A1 (en) | Systems and methods for performing automated feedback on potential real estate transactions | |
| US12002096B1 (en) | Artificial intelligence supported valuation platform | |
| CN111383091A (en) | Asset securitization pricing method and device | |
| US20130297475A1 (en) | Robust position detection, cause-and-effect and rule determinants to govern excessive risks for global regulatory compliance | |
| Al-Nefaie et al. | Bitcoin price forecasting and trading: Data analytics approaches | |
| US20180342014A1 (en) | Framework for decoupled development and management of scalably-mergeable trading strategies | |
| Kristóf | Sovereign default forecasting in the era of the COVID-19 crisis | |
| Dutta et al. | Volatility spillover and directionality in cryptocurrency and metal markets | |
| Deng et al. | Actions speak louder than words: Imputing users’ reputation from transaction history | |
| Chen et al. | Application of Markov Model‐Based IoT in Agricultural Insurance and Risk Management | |
| Killada | Data analytics using regression models for health insurance market place data | |
| Rath et al. | Emerging issues in fiscal sustainability in India: A study of Central government finances, 1979–1980 to 2018–2019 | |
| US20200202426A1 (en) | System and method for generating computerized educational tool | |
| Huang | Feature selection in credit scoring-a quadratic programming approach solving with bisection method based on Tabu search | |
| Simão | Machine Learning applied to credit risk assessment: Prediction of loan defaults | |
| Giansante et al. | A Statistical Mechanics Sampling of Financial Networks Under Bilateral Netting Constraints | |
| Tsao et al. | Smart Microfinance Platform Service for Migrant Workers | |
| O'Keefe | The Use of Machine Learning for Credit Risk Assessment | |
| Moreno Paredes | Developing insights related to portfolio management and individual investors by overcoming problems associated with analysing large scale financial data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FZDE | Discontinued |
Effective date: 20210831 |
|
| FZDE | Discontinued |
Effective date: 20210831 |